Increasing the Peak Signal-to-Noise Ratio in Encoding Medical Data with a Cover Image Using a Watermarking Algorithm Compared with Wavelet Algorithm

The proposed research aim is to utilise watermarking algorithms for enhancing the Peak Signal-to-Noise Ratio in the encapsulation of medical images, facilitating a comparison with the wavelet algorithm. This research study comprises two distinct methods: a Novel Watermarking method with a sample size of 10, and the utilisation of the Wavelet Algorithm method with a sample size of 10. Both aim to enhance the Peak Signal-to-Noise Ratio in encapsulating images, using the source Alaska2 Image Steganalysis Dataset from Kaggle. The training and testing subsets of the dataset were separated and used in the image encapsulation procedure. There were a total of 75,000 distinct classes in the dataset, which included 1000 images in the training dataset and an additional 1000 images in the validation dataset. The number of iterations for each algorithm is determined by the sample size, which is computed using ClinCalc. Using Gpower entails setting the pretest power to 0.8, alpha to 0.05, and preserving a 95% confidence level. In contrast to the wavelet method, which produces a typical accuracy of 41.3%, the Novel Watermarking algorithm employed for image encapsulation achieves an accuracy rate of 91.83%. In image encapsulation, the Novel Watermarking algorithm showed a notable performance advantage over the Wavelet technique, achieving a mean accuracy of 91.83%.